public_git
/
whisper.cpp
mirror of https://github.com/ggml-org/whisper.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
whisper.cpp/ggml/src/ggml-cuda
History
Oliver Simons d4a7ea1634 cuda : Fix Gemma3n not executed as CUDA_GRAPH on NVGPUs (llama/14741) 
* Fix Gemma3n not executed as CUDA_GRAPH on NVGPUs

Gemma3n uses Matrix-Matrix addition as part of their input processing,
wrongly triggering CUDA_GRAPH disablement on NVGPUs even when batch-size
of 1 is used.

* Exclude `project_per_layer_input` by matching node names

This ensures that all other graphs which don't exhibit this pattern do
not have their behavior changed.

* Revert unnecessary formatting changes
 		2025-07-20 00:23:50 +03:00
..
template-instances CUDA: FA support for Deepseek (Ampere or newer) (llama/13306) 2025-05-13 13:59:21 +03:00
vendors HIP : Add HIP 7.0+ compatibility for hipBLAS compute types (llama/14634) 2025-07-12 19:23:56 +03:00
CMakeLists.txt CUDA: FA support for Deepseek (Ampere or newer) (llama/13306) 2025-05-13 13:59:21 +03:00
acc.cu llama/ggml: add LLM training support (llama/10544) 2025-05-13 13:59:21 +03:00
acc.cuh whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
arange.cu whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
arange.cuh whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
argmax.cu cuda : optimize argmax (llama/10441) 2024-12-08 20:14:35 +02:00
argmax.cuh ggml/ex: calculate accuracy in graph, adapt MNIST (ggml/980) 2024-10-05 15:23:51 +03:00
argsort.cu ggml : reduce hash table reset cost (llama/8698) 2024-08-08 22:48:46 +03:00
argsort.cuh whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
binbcast.cu Support pure float16 add/sub/mul/div operations in the CUDA (and CPU) backend (ggml/1121) 2025-02-27 08:55:36 +02:00
binbcast.cuh ggml/examples: add backend support for numerical optimization (ggml/949) 2024-09-24 19:45:08 +03:00
clamp.cu cuda: unary ops as float + de-duplicate (ggml/1130) 2025-03-08 15:13:01 +02:00
clamp.cuh whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
common.cuh musa: fix build warnings (unused variable) (llama/14561) 2025-07-12 19:23:56 +03:00
concat.cu musa: fix all warnings, re-enable `-DLLAMA_FATAL_WARNINGS=ON` in ci and update doc (llama/12611) 2025-03-31 14:56:53 +03:00
concat.cuh whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
conv-transpose-1d.cu musa: fix all warnings, re-enable `-DLLAMA_FATAL_WARNINGS=ON` in ci and update doc (llama/12611) 2025-03-31 14:56:53 +03:00
conv-transpose-1d.cuh feat: cuda implementation for `ggml_conv_transpose_1d` (ggml/854) 2024-07-08 14:53:55 +03:00
conv2d-dw.cu CUDA: add conv_2d_dw (llama/14265) 2025-06-21 07:34:17 +03:00
conv2d-dw.cuh CUDA: add conv_2d_dw (llama/14265) 2025-06-21 07:34:17 +03:00
conv2d-transpose.cu CUDA: add conv_2d_transpose (llama/14287) 2025-06-21 07:34:17 +03:00
conv2d-transpose.cuh CUDA: add conv_2d_transpose (llama/14287) 2025-06-21 07:34:17 +03:00
convert.cu CUDA: add bf16 and f32 support to cublas_mul_mat_batched (llama/14361) 2025-07-01 17:54:53 +03:00
convert.cuh CUDA: add bf16 and f32 support to cublas_mul_mat_batched (llama/14361) 2025-07-01 17:54:53 +03:00
count-equal.cu ggml: fix zero division in ‘dne’ calculation in CUDA COUNT_EQUAL operator when ‘ne’ is small (#10213) 2024-11-15 15:21:04 +02:00
count-equal.cuh ggml/ex: calculate accuracy in graph, adapt MNIST (ggml/980) 2024-10-05 15:23:51 +03:00
cp-async.cuh CUDA: FA support for Deepseek (Ampere or newer) (llama/13306) 2025-05-13 13:59:21 +03:00
cpy-utils.cuh CUDA: set_rows + cpy.cu refactor (llama/14712) 2025-07-20 00:23:50 +03:00
cpy.cu CUDA: set_rows + cpy.cu refactor (llama/14712) 2025-07-20 00:23:50 +03:00
cpy.cuh ggml: Re-enable CUDA graphs in presence of CONT and DUP nodes (llama/12970) 2025-04-24 20:39:16 +03:00
cross-entropy-loss.cu CUDA: add dynamic shared mem to softmax, refactor general usage (llama/14497) 2025-07-12 19:23:56 +03:00
cross-entropy-loss.cuh ggml/examples: add backend support for numerical optimization (ggml/949) 2024-09-24 19:45:08 +03:00
dequantize.cuh whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
diagmask.cu whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
diagmask.cuh whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
fattn-common.cuh llama : add high-throughput mode (llama/14363) 2025-07-20 00:23:50 +03:00
fattn-mma-f16.cuh llama : add high-throughput mode (llama/14363) 2025-07-20 00:23:50 +03:00
fattn-tile-f16.cu llama : add high-throughput mode (llama/14363) 2025-07-20 00:23:50 +03:00
fattn-tile-f16.cuh whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
fattn-tile-f32.cu llama : add high-throughput mode (llama/14363) 2025-07-20 00:23:50 +03:00
fattn-tile-f32.cuh whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
fattn-vec-f16.cuh llama : add high-throughput mode (llama/14363) 2025-07-20 00:23:50 +03:00
fattn-vec-f32.cuh llama : add high-throughput mode (llama/14363) 2025-07-20 00:23:50 +03:00
fattn-wmma-f16.cu llama : add high-throughput mode (llama/14363) 2025-07-20 00:23:50 +03:00
fattn-wmma-f16.cuh CUDA: use mma PTX instructions for FlashAttention (llama/11583) 2025-02-03 22:00:57 +02:00
fattn.cu CUDA: faster Deepseek FA, add Turing support (llama/13435) 2025-05-19 14:58:39 +03:00
fattn.cuh whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
getrows.cu CUDA: add bf16 and i32 to getrows (llama/14529) 2025-07-12 19:23:56 +03:00
getrows.cuh CUDA: batched+noncont MMQ, refactor bs>1 MoE code (llama/13199) 2025-05-01 13:29:02 +03:00
ggml-cuda.cu cuda : Fix Gemma3n not executed as CUDA_GRAPH on NVGPUs (llama/14741) 2025-07-20 00:23:50 +03:00
gla.cu llama: add support for QRWKV6 model architecture (llama/11001) 2025-01-14 10:38:01 +02:00
gla.cuh llama: add support for QRWKV6 model architecture (llama/11001) 2025-01-14 10:38:01 +02:00
im2col.cu CUDA: fix 1D im2col, add tests (ggml/993) 2024-11-01 10:19:05 +02:00
im2col.cuh whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
mean.cu CUDA: add mean operation (llama/14313) 2025-07-01 17:54:53 +03:00
mean.cuh CUDA: add mean operation (llama/14313) 2025-07-01 17:54:53 +03:00
mma.cuh musa: fix all warnings, re-enable `-DLLAMA_FATAL_WARNINGS=ON` in ci and update doc (llama/12611) 2025-03-31 14:56:53 +03:00
mmq.cu CUDA: fix crash on large batch size for quant. MoE (llama/13537) 2025-05-19 14:58:39 +03:00
mmq.cuh CUDA: add dynamic shared mem to softmax, refactor general usage (llama/14497) 2025-07-12 19:23:56 +03:00
mmv.cu CUDA/HIP: optimize mmv paths taken for HIP devices (llama/14324) 2025-07-01 17:54:53 +03:00
mmv.cuh CUDA: mul_mat_v support for batch sizes > 1 (llama/14262) 2025-07-01 17:54:53 +03:00
mmvq.cu CUDA: fix crash with partial offloading of MoE (llama/13439) 2025-05-13 13:59:21 +03:00
mmvq.cuh CUDA: noncont MMVQ + batched bs1 MUL_MAT_ID (llama/13014) 2025-04-24 20:39:16 +03:00
norm.cu llama: Add support for RWKV v7 architecture (llama/12412) 2025-03-27 11:06:03 +02:00
norm.cuh llama: Add support for RWKV v7 architecture (llama/12412) 2025-03-27 11:06:03 +02:00
opt-step-adamw.cu ggml: new optimization interface (ggml/988) 2024-11-20 21:00:08 +02:00
opt-step-adamw.cuh ggml/examples: add backend support for numerical optimization (ggml/949) 2024-09-24 19:45:08 +03:00
out-prod.cu CPU/CUDA: fix (GQA) mul mat back, add CUDA support (llama/11380) 2025-02-03 22:00:57 +02:00
out-prod.cuh ggml/examples: add backend support for numerical optimization (ggml/949) 2024-09-24 19:45:08 +03:00
pad.cu musa: fix all warnings, re-enable `-DLLAMA_FATAL_WARNINGS=ON` in ci and update doc (llama/12611) 2025-03-31 14:56:53 +03:00
pad.cuh whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
pool2d.cu whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
pool2d.cuh whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
quantize.cu CUDA: fix crash on large batch size for quant. MoE (llama/13537) 2025-05-19 14:58:39 +03:00
quantize.cuh CUDA: batched+noncont MMQ, refactor bs>1 MoE code (llama/13199) 2025-05-01 13:29:02 +03:00
rope.cu cuda : fix rope with partial rotation and non-cont src (llama/14580) 2025-07-12 19:23:56 +03:00
rope.cuh RoPE: fix back, CUDA support for back + noncont. (llama/11240) 2025-02-03 22:00:57 +02:00
scale.cu ggml : add ggml_scale_bias (llama/14417) 2025-07-12 19:23:56 +03:00
scale.cuh whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
set-rows.cu CUDA: set_rows + cpy.cu refactor (llama/14712) 2025-07-20 00:23:50 +03:00
set-rows.cuh CUDA: add set rows for f32 and f16 (llama/14551) 2025-07-20 00:23:50 +03:00
softmax.cu CUDA: add dynamic shared mem to softmax, refactor general usage (llama/14497) 2025-07-12 19:23:56 +03:00
softmax.cuh CUDA: backwards pass for misc. ops, add tests (llama/11257) 2025-02-03 22:00:57 +02:00
ssm-conv.cu model : support LiquidAI LFM2 hybrid family (llama/14620) 2025-07-12 19:23:56 +03:00
ssm-conv.cuh ggml : faster ssm scan (llama/10558) 2025-04-02 15:51:57 +03:00
ssm-scan.cu cuda : support Falcon-H1 state size for SSM_SCAN (llama/14602) 2025-07-12 19:23:56 +03:00
ssm-scan.cuh ggml : faster ssm scan (llama/10558) 2025-04-02 15:51:57 +03:00
sum.cu llama/ggml: add LLM training support (llama/10544) 2025-05-13 13:59:21 +03:00
sum.cuh tests: add gradient tests for all backends (ggml/932) 2024-09-24 19:45:08 +03:00
sumrows.cu CUDA: add mean operation (llama/14313) 2025-07-01 17:54:53 +03:00
sumrows.cuh CUDA: add mean operation (llama/14313) 2025-07-01 17:54:53 +03:00
tsembd.cu whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
tsembd.cuh whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
unary.cu cuda : add ELU support (llama/14657) 2025-07-20 00:23:50 +03:00
unary.cuh cuda : add ELU support (llama/14657) 2025-07-20 00:23:50 +03:00
upscale.cu CUDA: add bilinear interpolation for upscale (llama/14563) 2025-07-12 19:23:56 +03:00
upscale.cuh whisper : reorganize source code + improve CMake (#2256) 2024-06-26 19:34:09 +03:00
vecdotq.cuh CUDA: noncont MMVQ + batched bs1 MUL_MAT_ID (llama/13014) 2025-04-24 20:39:16 +03:00
wkv.cu llama: Add support for RWKV v7 architecture (llama/12412) 2025-03-27 11:06:03 +02:00
wkv.cuh llama: Add support for RWKV v7 architecture (llama/12412) 2025-03-27 11:06:03 +02:00